Nicolas Perony

Shimon Vainer, Mark Boss, Mathias Parger et al.

Graphics pipelines require physically-based rendering (PBR) materials, yet current 3D content generation approaches are built on RGB models. We propose to model the PBR image distribution directly, avoiding photometric inaccuracies in RGB generation and the inherent ambiguity in extracting PBR from RGB. As existing paradigms for cross-modal fine-tuning are not suited for PBR generation due to both a lack of data and the high dimensionality of the output modalities, we propose to train a new PBR model that is tightly linked to a frozen RGB model using a novel cross-network communication paradigm. As the base RGB model is fully frozen, the proposed method retains its general performance and remains compatible with e.g. IPAdapters for that base model.

Mael Leroux, Orestes Gutierrez Al-Khudhairy, Nicolas Perony et al.

Individual vocal differences are ubiquitous in the animal kingdom. In humans, these differences pervade the entire vocal repertoire and constitute a "voice print". Apes, our closest-living relatives, possess individual signatures within specific call types, but the potential for a unique voice print has been little investigated. This is partially attributed to the limitations associated with extracting meaningful features from small data sets. Advances in machine learning have highlighted an alternative to traditional acoustic features, namely pre-trained learnt extractors. Here, we present an approach building on these developments: leveraging a feature extractor based on a deep neural network trained on over 10,000 human voice prints to provide an informative space over which we identify chimpanzee voice prints. We compare our results with those obtained by using traditional acoustic features and discuss the benefits of our methodology and the significance of our findings for the identification of "voice prints" in non-human animals.